re PR target/80510 (Optimize Power7/power8 Altivec load/stores)

[gcc]
2017-06-23  Michael Meissner  <meissner@linux.vnet.ibm.com>

	PR target/80510
	* config/rs6000/rs6000.md (ALTIVEC_DFORM): Do not allow DImode in
	32-bit, since indexed is not valid for DImode.
	(mov<mode>_hardfloat32): Reorder ISA 2.07 load/stores before ISA
	3.0 d-form load/stores to be the same as mov<mode>_hardfloat64.
	(define_peephole2 for Altivec d-form load): Add 32-bit support.
	(define_peephole2 for Altivec d-form store): Likewise.

[gcc/testsuite]
2017-06-23  Michael Meissner  <meissner@linux.vnet.ibm.com>

	PR target/80510
	* gcc.target/powerpc/pr80510-1.c: Allow test to run on 32-bit.
	* gcc.target/powerpc/pr80510-2.c: Likewise.

From-SVN: r249607

5 files changed, 33 insertions, 21 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3e43b44..5019018 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,13 @@
 2017-06-23  Michael Meissner  <meissner@linux.vnet.ibm.com>
 
+	PR target/80510
+	* config/rs6000/rs6000.md (ALTIVEC_DFORM): Do not allow DImode in
+	32-bit, since indexed is not valid for DImode.
+	(mov<mode>_hardfloat32): Reorder ISA 2.07 load/stores before ISA
+	3.0 d-form load/stores to be the same as mov<mode>_hardfloat64.
+	(define_peephole2 for Altivec d-form load): Add 32-bit support.
+	(define_peephole2 for Altivec d-form store): Likewise.
+
 	PR ipa/81185
 	* multiple_target.c (create_dispatcher_calls): Only create the
 	dispatcher call if the function is the default clone of a
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 8e1b460..f78dbf9 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -690,7 +690,9 @@
 ;; Iterator to optimize the following cases:
 ;;	D-form load to FPR register & move to Altivec register
 ;;	Move Altivec register to FPR register and store
-(define_mode_iterator ALTIVEC_DFORM [DI DF SF])
+(define_mode_iterator ALTIVEC_DFORM [DF
+				     SF
+				     (DI "TARGET_POWERPC64")])
 
 
 ;; Start with fixed-point load and store insns.  Here we put only the more
@@ -7391,8 +7393,8 @@
 ;; except for 0.0 which can be created on VSX with an xor instruction.
 
 (define_insn "*mov<mode>_hardfloat32"
-  [(set (match_operand:FMOVE64 0 "nonimmediate_operand" "=m,d,d,<f64_av>,Z,<f64_p9>,wY,<f64_vsx>,<f64_vsx>,!r,Y,r,!r")
-	(match_operand:FMOVE64 1 "input_operand" "d,m,d,Z,<f64_av>,wY,<f64_p9>,<f64_vsx>,<zero_fp>,<zero_fp>,r,Y,r"))]
+  [(set (match_operand:FMOVE64 0 "nonimmediate_operand" "=m,d,d,<f64_p9>,wY,<f64_av>,Z,<f64_vsx>,<f64_vsx>,!r,Y,r,!r")
+	(match_operand:FMOVE64 1 "input_operand" "d,m,d,wY,<f64_p9>,Z,<f64_av>,<f64_vsx>,<zero_fp>,<zero_fp>,r,Y,r"))]
   "! TARGET_POWERPC64 && TARGET_HARD_FLOAT && TARGET_DOUBLE_FLOAT 
    && (gpc_reg_operand (operands[0], <MODE>mode)
        || gpc_reg_operand (operands[1], <MODE>mode))"
@@ -7400,10 +7402,10 @@
    stfd%U0%X0 %1,%0
    lfd%U1%X1 %0,%1
    fmr %0,%1
-   lxsd%U1x %x0,%y1
-   stxsd%U0x %x1,%y0
    lxsd %0,%1
    stxsd %1,%0
+   lxsd%U1x %x0,%y1
+   stxsd%U0x %x1,%y0
    xxlor %x0,%x1,%x1
    xxlxor %x0,%x0,%x0
    #
@@ -13967,13 +13969,13 @@
 ;;	LXSDX 32,3,9
 
 (define_peephole2
-  [(match_scratch:DI 0 "b")
+  [(match_scratch:P 0 "b")
    (set (match_operand:ALTIVEC_DFORM 1 "fpr_reg_operand")
 	(match_operand:ALTIVEC_DFORM 2 "simple_offsettable_mem_operand"))
    (set (match_operand:ALTIVEC_DFORM 3 "altivec_register_operand")
 	(match_dup 1))]
-  "TARGET_VSX && TARGET_POWERPC64 && TARGET_UPPER_REGS_<MODE>
-   && !TARGET_P9_DFORM_SCALAR && peep2_reg_dead_p (2, operands[1])"
+  "TARGET_VSX && TARGET_UPPER_REGS_<MODE> && !TARGET_P9_DFORM_SCALAR
+   && peep2_reg_dead_p (2, operands[1])"
   [(set (match_dup 0)
 	(match_dup 4))
    (set (match_dup 3)
@@ -13988,7 +13990,7 @@
   add_op0 = XEXP (addr, 0);
   add_op1 = XEXP (addr, 1);
   gcc_assert (REG_P (add_op0));
-  new_addr = gen_rtx_PLUS (DImode, add_op0, tmp_reg);
+  new_addr = gen_rtx_PLUS (Pmode, add_op0, tmp_reg);
 
   operands[4] = add_op1;
   operands[5] = change_address (mem, <MODE>mode, new_addr);
@@ -14004,13 +14006,13 @@
 ;;	STXSDX 32,3,9
 
 (define_peephole2
-  [(match_scratch:DI 0 "b")
+  [(match_scratch:P 0 "b")
    (set (match_operand:ALTIVEC_DFORM 1 "fpr_reg_operand")
 	(match_operand:ALTIVEC_DFORM 2 "altivec_register_operand"))
    (set (match_operand:ALTIVEC_DFORM 3 "simple_offsettable_mem_operand")
 	(match_dup 1))]
-  "TARGET_VSX && TARGET_POWERPC64 && TARGET_UPPER_REGS_<MODE>
-   && !TARGET_P9_DFORM_SCALAR && peep2_reg_dead_p (2, operands[1])"
+  "TARGET_VSX && TARGET_UPPER_REGS_<MODE> && !TARGET_P9_DFORM_SCALAR
+   && peep2_reg_dead_p (2, operands[1])"
   [(set (match_dup 0)
 	(match_dup 4))
    (set (match_dup 5)
@@ -14025,7 +14027,7 @@
   add_op0 = XEXP (addr, 0);
   add_op1 = XEXP (addr, 1);
   gcc_assert (REG_P (add_op0));
-  new_addr = gen_rtx_PLUS (DImode, add_op0, tmp_reg);
+  new_addr = gen_rtx_PLUS (Pmode, add_op0, tmp_reg);
 
   operands[4] = add_op1;
   operands[5] = change_address (mem, <MODE>mode, new_addr);
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 8c55862..a269478 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+2017-06-23  Michael Meissner  <meissner@linux.vnet.ibm.com>
+
+	PR target/80510
+	* gcc.target/powerpc/pr80510-1.c: Allow test to run on 32-bit.
+	* gcc.target/powerpc/pr80510-2.c: Likewise.
+
 2017-06-22  Jeff Law  <law@redhat.com>
 
 	* gcc.c-torture/compile/stack-check-1.c: Require "untyped_assembly".
diff --git a/gcc/testsuite/gcc.target/powerpc/pr80510-1.c b/gcc/testsuite/gcc.target/powerpc/pr80510-1.c
index d832e92..deb51ac 100644
--- a/gcc/testsuite/gcc.target/powerpc/pr80510-1.c
+++ b/gcc/testsuite/gcc.target/powerpc/pr80510-1.c
@@ -1,4 +1,4 @@
-/* { dg-do compile { target { powerpc*-*-* && lp64 } } } */
+/* { dg-do compile { target { powerpc*-*-* } } } */
 /* { dg-skip-if "" { powerpc*-*-darwin* } } */
 /* { dg-require-effective-target powerpc_vsx_ok } */
 /* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power7" } } */
@@ -6,9 +6,7 @@
 
 /* Make sure that STXSDX is generated for double scalars in Altivec registers
    on power7 instead of moving the value to a FPR register and doing a X-FORM
-   store.
-
-   32-bit currently does not have support for STXSDX in the mov{df,dd} patterns.  */
+   store.  */
 
 #ifndef TYPE
 #define TYPE double
diff --git a/gcc/testsuite/gcc.target/powerpc/pr80510-2.c b/gcc/testsuite/gcc.target/powerpc/pr80510-2.c
index 83a186b..b4d2491 100644
--- a/gcc/testsuite/gcc.target/powerpc/pr80510-2.c
+++ b/gcc/testsuite/gcc.target/powerpc/pr80510-2.c
@@ -1,4 +1,4 @@
-/* { dg-do compile { target { powerpc*-*-* && lp64 } } } */
+/* { dg-do compile { target { powerpc*-*-* } } } */
 /* { dg-skip-if "" { powerpc*-*-darwin* } } */
 /* { dg-require-effective-target powerpc_p8vector_ok } */
 /* { dg-skip-if "do not override -mcpu" { powerpc*-*-* } { "-mcpu=*" } { "-mcpu=power8" } } */
@@ -6,9 +6,7 @@
 
 /* Make sure that STXSSPX is generated for float scalars in Altivec registers
    on power7 instead of moving the value to a FPR register and doing a X-FORM
-   store.
-
-   32-bit currently does not have support for STXSSPX in the mov{sf,sd} patterns.  */
+   store.  */
 
 #ifndef TYPE
 #define TYPE float